X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=chopseqscommand.cpp;h=1133ff46a8620817708c72607141691d59d5c4ac;hb=8f909cf6870cc2e4d8ed8cff69a203f6f83a160b;hp=536aec910c9cc79b54caf34b1f60333b277e8c00;hpb=3604ddb078ae09215ec1ddc2b8c183232e3b5f89;p=mothur.git diff --git a/chopseqscommand.cpp b/chopseqscommand.cpp index 536aec9..1133ff4 100644 --- a/chopseqscommand.cpp +++ b/chopseqscommand.cpp @@ -11,7 +11,54 @@ #include "sequence.hpp" //********************************************************************************************************************** - +vector ChopSeqsCommand::getValidParameters(){ + try { + string AlignArray[] = {"fasta","short","numbases","countgaps","keep","outputdir","inputdir"}; + vector myArray (AlignArray, AlignArray+(sizeof(AlignArray)/sizeof(string))); + return myArray; + } + catch(exception& e) { + m->errorOut(e, "ChopSeqsCommand", "getValidParameters"); + exit(1); + } +} +//********************************************************************************************************************** +ChopSeqsCommand::ChopSeqsCommand(){ + try { + //initialize outputTypes + vector tempOutNames; + outputTypes["fasta"] = tempOutNames; + outputTypes["accnos"] = tempOutNames; + } + catch(exception& e) { + m->errorOut(e, "ChopSeqsCommand", "ChopSeqsCommand"); + exit(1); + } +} +//********************************************************************************************************************** +vector ChopSeqsCommand::getRequiredParameters(){ + try { + string Array[] = {"fasta","numbases"}; + vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); + return myArray; + } + catch(exception& e) { + m->errorOut(e, "ChopSeqsCommand", "getRequiredParameters"); + exit(1); + } +} +//********************************************************************************************************************** +vector ChopSeqsCommand::getRequiredFiles(){ + try { + vector myArray; + return myArray; + } + catch(exception& e) { + m->errorOut(e, "ChopSeqsCommand", "getRequiredFiles"); + exit(1); + } +} +//********************************************************************************************************************** ChopSeqsCommand::ChopSeqsCommand(string option) { try { abort = false; @@ -21,7 +68,7 @@ ChopSeqsCommand::ChopSeqsCommand(string option) { else { //valid paramters for this command - string Array[] = {"fasta","numbases","keep","outputdir","inputdir"}; + string Array[] = {"fasta","numbases","countgaps","keep","short","outputdir","inputdir"}; vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); OptionParser parser(option); @@ -35,9 +82,11 @@ ChopSeqsCommand::ChopSeqsCommand(string option) { if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; } } - //if the user changes the output directory command factory will send this info to us in the output parameter - outputDir = validParameter.validFile(parameters, "outputdir", false); if (outputDir == "not found"){ outputDir = ""; } - + //initialize outputTypes + vector tempOutNames; + outputTypes["fasta"] = tempOutNames; + outputTypes["accnos"] = tempOutNames; + //if the user changes the input directory command factory will send this info to us in the output parameter string inputDir = validParameter.validFile(parameters, "inputdir", false); if (inputDir == "not found"){ inputDir = ""; } @@ -46,7 +95,7 @@ ChopSeqsCommand::ChopSeqsCommand(string option) { it = parameters.find("fasta"); //user has given a template file if(it != parameters.end()){ - path = hasPath(it->second); + path = m->hasPath(it->second); //if the user has not given a path then, add inputdir. else leave path alone. if (path == "") { parameters["fasta"] = inputDir + it->second; } } @@ -57,8 +106,17 @@ ChopSeqsCommand::ChopSeqsCommand(string option) { if (fastafile == "not open") { abort = true; } else if (fastafile == "not found") { m->mothurOut("You must provide a fasta file."); m->mothurOutEndLine(); abort = true; } + //if the user changes the output directory command factory will send this info to us in the output parameter + outputDir = validParameter.validFile(parameters, "outputdir", false); if (outputDir == "not found"){ outputDir = m->hasPath(fastafile); } + string temp = validParameter.validFile(parameters, "numbases", false); if (temp == "not found") { temp = "0"; } convert(temp, numbases); + + temp = validParameter.validFile(parameters, "countgaps", false); if (temp == "not found") { temp = "f"; } + countGaps = m->isTrue(temp); + + temp = validParameter.validFile(parameters, "short", false); if (temp == "not found") { temp = "f"; } + Short = m->isTrue(temp); keep = validParameter.validFile(parameters, "keep", false); if (keep == "not found") { keep = "front"; } @@ -76,10 +134,13 @@ ChopSeqsCommand::ChopSeqsCommand(string option) { void ChopSeqsCommand::help(){ try { m->mothurOut("The chop.seqs command reads a fasta file and outputs a .chop.fasta containing the trimmed sequences.\n"); - m->mothurOut("The chop.seqs command parameters are fasta, numbases, and keep. fasta and numbases are required required.\n"); + m->mothurOut("The chop.seqs command parameters are fasta, numbases, countgaps and keep. fasta and numbases are required required.\n"); m->mothurOut("The chop.seqs command should be in the following format: chop.seqs(fasta=yourFasta, numbases=yourNum, keep=yourKeep).\n"); m->mothurOut("The numbases parameter allows you to specify the number of bases you want to keep.\n"); m->mothurOut("The keep parameter allows you to specify whether you want to keep the front or the back of your sequence, default=front.\n"); + m->mothurOut("The countgaps parameter allows you to specify whether you want to count gaps as bases, default=false.\n"); + m->mothurOut("The short parameter allows you to specify you want to keep sequences that are too short to chop, default=false.\n"); + m->mothurOut("For example, if you ran chop.seqs with numbases=200 and short=t, if a sequence had 100 bases mothur would keep the sequence rather than eliminate it.\n"); m->mothurOut("Example chop.seqs(fasta=amazon.fasta, numbases=200, keep=front).\n"); m->mothurOut("Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFasta).\n\n"); } @@ -96,17 +157,17 @@ int ChopSeqsCommand::execute(){ if (abort == true) { return 0; } - string outputFileName = outputDir + getRootName(getSimpleName(fastafile)) + "chop.fasta"; - string outputFileNameAccnos = outputDir + getRootName(getSimpleName(fastafile)) + "chop.accnos"; + string outputFileName = outputDir + m->getRootName(m->getSimpleName(fastafile)) + "chop.fasta"; + string outputFileNameAccnos = outputDir + m->getRootName(m->getSimpleName(fastafile)) + "chop.accnos"; ofstream out; - openOutputFile(outputFileName, out); + m->openOutputFile(outputFileName, out); ofstream outAcc; - openOutputFile(outputFileNameAccnos, outAcc); + m->openOutputFile(outputFileNameAccnos, outAcc); ifstream in; - openInputFile(fastafile, in); + m->openInputFile(fastafile, in); bool wroteAccnos = false; @@ -114,7 +175,7 @@ int ChopSeqsCommand::execute(){ Sequence seq(in); - if (m->control_pressed) { in.close(); out.close(); outAcc.close(); remove(outputFileName.c_str()); remove(outputFileNameAccnos.c_str()); return 0; } + if (m->control_pressed) { outputTypes.clear(); in.close(); out.close(); outAcc.close(); remove(outputFileName.c_str()); remove(outputFileNameAccnos.c_str()); return 0; } if (seq.getName() != "") { string newSeqString = getChopped(seq); @@ -134,9 +195,9 @@ int ChopSeqsCommand::execute(){ m->mothurOutEndLine(); m->mothurOut("Output File Name: "); m->mothurOutEndLine(); - m->mothurOut(outputFileName); m->mothurOutEndLine(); + m->mothurOut(outputFileName); m->mothurOutEndLine(); outputNames.push_back(outputFileName); outputTypes["fasta"].push_back(outputFileName); - if (wroteAccnos) { m->mothurOut(outputFileNameAccnos); m->mothurOutEndLine(); } + if (wroteAccnos) { m->mothurOut(outputFileNameAccnos); m->mothurOutEndLine(); outputNames.push_back(outputFileNameAccnos); outputTypes["accnos"].push_back(outputFileNameAccnos); } else { remove(outputFileNameAccnos.c_str()); } m->mothurOutEndLine(); @@ -154,60 +215,113 @@ string ChopSeqsCommand::getChopped(Sequence seq) { try { string temp = seq.getAligned(); string tempUnaligned = seq.getUnaligned(); - - //if needed trim sequence - if (keep == "front") {//you want to keep the beginning - int tempLength = tempUnaligned.length(); + + if (countGaps) { + //if needed trim sequence + if (keep == "front") {//you want to keep the beginning + int tempLength = temp.length(); - if (tempLength > numbases) { //you have enough bases to remove some - - int stopSpot = 0; - int numBasesCounted = 0; + if (tempLength > numbases) { //you have enough bases to remove some - for (int i = 0; i < temp.length(); i++) { - //eliminate N's - if (toupper(temp[i]) == 'N') { - temp[i] == '.'; - tempLength--; - if (tempLength < numbases) { stopSpot = 0; break; } - } + int stopSpot = 0; + int numBasesCounted = 0; - if(isalpha(temp[i])) { numBasesCounted++; } + for (int i = 0; i < temp.length(); i++) { + //eliminate N's + if (toupper(temp[i]) == 'N') { temp[i] == '.'; } + + numBasesCounted++; + + if (numBasesCounted >= numbases) { stopSpot = i; break; } + } - if (numBasesCounted >= numbases) { stopSpot = i; break; } + if (stopSpot == 0) { temp = ""; } + else { temp = temp.substr(0, stopSpot); } + + }else { + if (!Short) { temp = ""; } //sequence too short } - - if (stopSpot == 0) { temp = ""; } - else { temp = temp.substr(0, stopSpot); } + }else { //you are keeping the back + int tempLength = temp.length(); + if (tempLength > numbases) { //you have enough bases to remove some + + int stopSpot = 0; + int numBasesCounted = 0; + + for (int i = (temp.length()-1); i >= 0; i--) { + //eliminate N's + if (toupper(temp[i]) == 'N') { temp[i] == '.'; } - }else { temp = ""; } //sequence too short - - }else { //you are keeping the back - int tempLength = tempUnaligned.length(); - if (tempLength > numbases) { //you have enough bases to remove some + numBasesCounted++; + + if (numBasesCounted >= numbases) { stopSpot = i; break; } + } - int stopSpot = 0; - int numBasesCounted = 0; + if (stopSpot == 0) { temp = ""; } + else { temp = temp.substr(stopSpot+1); } + }else { + if (!Short) { temp = ""; } //sequence too short + } + } + + }else{ - for (int i = (temp.length()-1); i >= 0; i--) { - //eliminate N's - if (toupper(temp[i]) == 'N') { - temp[i] == '.'; - tempLength--; - if (tempLength < numbases) { stopSpot = 0; break; } + //if needed trim sequence + if (keep == "front") {//you want to keep the beginning + int tempLength = tempUnaligned.length(); + + if (tempLength > numbases) { //you have enough bases to remove some + + int stopSpot = 0; + int numBasesCounted = 0; + + for (int i = 0; i < temp.length(); i++) { + //eliminate N's + if (toupper(temp[i]) == 'N') { + temp[i] == '.'; + tempLength--; + if (tempLength < numbases) { stopSpot = 0; break; } + } + + if(isalpha(temp[i])) { numBasesCounted++; } + + if (numBasesCounted >= numbases) { stopSpot = i; break; } } - if(isalpha(temp[i])) { numBasesCounted++; } + if (stopSpot == 0) { temp = ""; } + else { temp = temp.substr(0, stopSpot); } + + }else { + if (!Short) { temp = ""; } //sequence too short + } + }else { //you are keeping the back + int tempLength = tempUnaligned.length(); + if (tempLength > numbases) { //you have enough bases to remove some + + int stopSpot = 0; + int numBasesCounted = 0; + + for (int i = (temp.length()-1); i >= 0; i--) { + //eliminate N's + if (toupper(temp[i]) == 'N') { + temp[i] == '.'; + tempLength--; + if (tempLength < numbases) { stopSpot = 0; break; } + } + + if(isalpha(temp[i])) { numBasesCounted++; } - if (numBasesCounted >= numbases) { stopSpot = i; break; } + if (numBasesCounted >= numbases) { stopSpot = i; break; } + } + + if (stopSpot == 0) { temp = ""; } + else { temp = temp.substr(stopSpot+1); } + }else { + if (!Short) { temp = ""; } //sequence too short } - - if (stopSpot == 0) { temp = ""; } - else { temp = temp.substr(stopSpot+1); } } - else { temp = ""; } //sequence too short } - + return temp; } catch(exception& e) {